Publications

2025

  1. NeoBERT: A Next-Generation BERT
    Lola Le Breton, Quentin Fournier, Mariam El Mezouar, and Sarath Chandar
    arXiv preprint arXiv:2502.19587, 2025
  2. Structure-Aligned Protein Language Model
    Can Chen, David Heurtel-Depeiges, Robert M Vernon, Christopher James Langmead, Yoshua Bengio, and Quentin Fournier
    arXiv preprint arXiv:2505.16896, 2025
  3. Small Encoders Can Rival Large Decoders in Detecting Groundedness
    Istabrak Abbes, Gabriele Prato, Quentin Fournier, Fernando Rodriguez, Alaa Boukhary, Adam Elwood, and Sarath Chandar
    arXiv preprint arXiv:2506.21288, 2025
  4. Combining Domain and Alignment Vectors Provides Better Knowledge-Safety Trade-offs in LLMs
    Megh Thakkar, Quentin Fournier, Matthew Riemer, Pin-Yu Chen, Amal Zouaq, Payel Das, and Sarath Chandar
    In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), 2025
  5. CADmium: Fine-Tuning Code Language Models for Text-Driven Sequential CAD Design
    Prashant Govindarajan, Davide Baldelli, Jay Pathak, Quentin Fournier, and Sarath Chandar
    arXiv preprint arXiv:2507.09792, 2025

2024

  1. Predicting the Impact of Model Expansion through the Minima Manifold: A Loss Landscape Perspective
    Pranshu Malviya, Jerry Huang, Quentin Fournier, and Sarath Chandar
    2024
  2. A deep dive into the trade-offs of parameter-efficient preference alignment techniques
    Megh Thakkar, Quentin Fournier, Matthew D Riemer, Pin-Yu Chen, Amal Zouaq, Payel Das, and Sarath Chandar
    arXiv preprint arXiv:2406.04879, 2024
  3. Exploring quantization for efficient pre-training of transformer language models
    Kamran Chitsaz, Quentin Fournier, Gonçalo Mordido, and Sarath Chandar
    arXiv preprint arXiv:2407.11722, 2024
  4. Combining domain and alignment vectors to achieve better knowledge-safety trade-offs in llms
    Megh Thakkar, Quentin Fournier, Matthew Riemer, Pin-Yu Chen, Amal Zouaq, Payel Das, and Sarath Chandar
    arXiv preprint arXiv:2411.06824, 2024
  5. Protein language models: Is scaling necessary?
    Quentin Fournier, Robert M Vernon, Almer Sloot, Benjamin Schulz, Sarath Chandar, and Christopher James Langmead
    bioRxiv, 2024
  6. Interpolate: How Resetting Active Neurons can also improve Generalizability in Online Learning
    Pranshu Malviya, Darshan Patil, Maryam Hashemzadeh, Quentin Fournier, and Sarath Chandar
    2024

2023

  1. A practical survey on faster and lighter transformers
    Quentin Fournier, Gaétan Marceau Caron, and Daniel Aloise
    ACM Computing Surveys, 2023
  2. Detection of microservice-based software anomalies based on OpenTracing in cloud
    Mohammad Khanahmadi, Alireza Shameli-Sendi, Masoume Jabbarifar, Quentin Fournier, and Michel Dagenais
    Software: Practice and Experience, 2023
  3. Distributed computation of the critical path from execution traces
    Pierre-Frédérick Denys, Quentin Fournier, and Michel Dagenais
    Software: Practice and Experience, 2023
  4. Language models for novelty detection in system call traces
    Quentin Fournier, Daniel Aloise, and Leandro R Costa
    arXiv preprint arXiv:2309.02206, 2023
  5. Energy and carbon-aware initial VM placement in geographically distributed cloud data centers
    Ehsan Khodayarseresht, Alireza Shameli-Sendi, Quentin Fournier, and Michel Dagenais
    Sustainable Computing: Informatics and Systems, 2023

2022

  1. Machine Learning for Anomaly Detection in Kernel Traces
    Quentin Fournier
    2022

2021

  1. On improving deep learning trace analysis with system call arguments
    Quentin Fournier, Daniel Aloise, Seyed Vahid Azhari, and François Tetreault
    In 2021 IEEE/ACM 18th International Conference on Mining Software Repositories (MSR), 2021
  2. Automated cause analysis of latency outliers using system-level dependency graphs
    Sneh Patel, Brendan Park, Naser Ezzati-Jivan, and Quentin Fournier
    In 2021 IEEE 21st International Conference on Software Quality, Reliability and Security (QRS), 2021

2020

  1. Depgraph: Localizing performance bottlenecks in multi-core applications using waiting dependency graphs and software tracing
    Naser Ezzati-Jivan, Quentin Fournier, Michel R Dagenais, and Abdelwahab Hamou-Lhadj
    In 2020 IEEE 20th International Working Conference on Source Code Analysis and Manipulation (SCAM), 2020

2019

  1. Empirical comparison between autoencoders and traditional dimensionality reduction methods
    Quentin Fournier and Daniel Aloise
    In 2019 IEEE Second International Conference on Artificial Intelligence and Knowledge Engineering (AIKE), 2019
  2. Automatic cause detection of performance problems in web applications
    Quentin Fournier, Naser Ezzati-Jivan, Daniel Aloise, and Michel R Dagenais
    In 2019 IEEE International Symposium on Software Reliability Engineering Workshops (ISSREW), 2019